logo.jpg

Employee Personality assessment¶

About Dataset:

  • Employee_ID : Contains Unique_id for employee.
  • Question_ID : Contains 3 question mentioned as 101(personal value), 102(Curent cultural values), 103(Desired cultural Values).
  • Selected values : it contain set of Option values selected for each question.
In [1]:
# importing all required packages
import pandas as pd # for pandas
import numpy as np #for array
import matplotlib as plt # for visualization
import matplotlib.pyplot as plt # for visualization
import seaborn as sns # for visualization
import bokeh as bk # for viz.
import missingno as mn # for table visualization
%matplotlib inline
import plotly.express as px
import plotly.graph_objects as go # Visualization

Importing the dataset

In [2]:
df = pd.read_csv('Culturelytics_Task-data analytics.csv') # loading datafranme

df
Out[2]:
Employee_ID Question_ID Selected_Value Value_Order
0 2385 101 Accountability 1
1 2385 101 Achievement 2
2 2385 101 Commitment 3
3 2385 101 Cost Reduction 4
4 2385 101 Efficiency 5
... ... ... ... ...
72145 1092 103 Cost Reduction 6
72146 1092 103 Financial Stability 7
72147 1092 103 Global Thinking 8
72148 1092 103 Influence 9
72149 1092 103 Leadership Development 10

72150 rows × 4 columns

In [3]:
df.describe() #describing the data
Out[3]:
Employee_ID Question_ID Value_Order
count 72150.000000 72150.000000 72150.000000
mean 1944.217879 102.000000 5.500000
std 1049.797010 0.816502 2.872301
min 147.000000 101.000000 1.000000
25% 1027.000000 101.000000 3.000000
50% 1938.000000 102.000000 5.500000
75% 2852.000000 103.000000 8.000000
max 3747.000000 103.000000 10.000000
In [4]:
df.info() # information of data

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 72150 entries, 0 to 72149
Data columns (total 4 columns):
 #   Column          Non-Null Count  Dtype 
---  ------          --------------  ----- 
 0   Employee_ID     72150 non-null  int64 
 1   Question_ID     72150 non-null  int64 
 2   Selected_Value  72150 non-null  object
 3   Value_Order     72150 non-null  int64 
dtypes: int64(3), object(1)
memory usage: 2.2+ MB
In [5]:
df.isna().sum() # sum of null values
Out[5]:
Employee_ID       0
Question_ID       0
Selected_Value    0
Value_Order       0
dtype: int64
In [6]:
# Calculate the correlation matrix
corr_matrix = df.corr()
plt.figure(figsize=(10, 8))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm')
plt.title('Correlation Heatmap')
plt.show()

Correlation Matrix¶

it indicates there is no co-relation in the data there are 4 different columns

Observation from the dataset¶

The Dataset have 3 question as following

  • personal values: Quention_ID 101, where the employee selects his personal quality in order in Value_Order column and as based on his selection we get Order_Value such that the first selected value have higher weightage.
  • Current cultural values: Question_ID 102, where the Employee select the values based on the current culture of the organisation in order in Value_Order column and as based on his selection we get Order_Value such that the first selected value have higher weightage.
  • Desired cultural values: Question_ID 103, where the Employee select the values based on the required uplifments and the required cultural value that are to be practiced for the growth in order in Value_Order column and as based on his selection we get Order_Value such that the first selected value have higher weightage.

Now based on this we have Four different Dashboards¶

Employee Assessment

Current Organisational Culture

Desired Organisational Culture For Future

Result Board

Dashboard1: Employee Assessment¶

  • Leadership Assessment : Tells the how much is that employee capable of leadership skills.
  • Team Collaboration Assessment : Tells how good is the employee is in his team collaboration skills.
  • Employee Engagement Assessment : Tells engagement of emloyee in the activities.
  • Innovation mindset Assessment : Tells how much innovative mind set does the employee have.

q1.jpeg

In [7]:
# selecting Employee
employee_id = int(input("Enter the Employee ID: "))
# Few examples of Employee Id in dataset are selec in these
# 3200, 242, 3606, 1783, 2230, 528, 2098 , 900, 1547 ,303 , 323, 3583, 1718, 268,3547, 1703,235,1289,3723,3350

Enter the Employee ID: 2814
In [8]:
import plotly.graph_objects as go

# defing qualities
assessments = {
    'Leadership Assessment': ['Accountability', 'Achievement', 'Commitment', 'Integrity', 'Transparency', 'Vision', 'Leadership Development', 'Team Work'],
    'Team Collaboration Assessment': ['Teamwork', 'Trust', 'Conflict Resolution', 'Inclusiveness', 'Coaching/Mentoring', 'Communication', 'Reliability'],
    'Employee Engagement Assessment': ['Empowerment', 'Recognition', 'Information Sharing', 'Well-Being', 'Sustainability', 'Community Involvement', 'Employee Engagement'],
    'Innovation Mindset Assessment': ['Creativity', 'Continuous Improvement', 'Long-Term Perspective', 'Open Communication', 'Risk-Taking', 'Change Averse', 'Decisiveness']
}

def calculate_overall_score(employee_id, qualities):
    filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
    total_points = len(filtered_data) * 10
    points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum()
    percentage_scores = (points_scored / total_points) * 100
    overall_score = percentage_scores.sum()
    return overall_score

# list to store overall scores
overall_scores = []

# assessments for the given Employee ID
for assessment, qualities in assessments.items():
    overall_score = calculate_overall_score(employee_id, qualities)
    overall_scores.append(overall_score)

#  plotly radial chart
fig = go.Figure()

# radial chart traces
fig.add_trace(go.Scatterpolar(
    r=overall_scores,
    theta=list(assessments.keys()),
    fill='toself',
    name='Score',
    marker=dict(color='purple')
))

# layout properties
fig.update_layout(
    polar=dict(
        radialaxis=dict(
            visible=True,
            range=[0, 100]
        )
    ),
    showlegend=False
)

fig.show()
In [9]:
# Ploting The Selected employees Leadership Skill
qualities = ['Accountability', 'Achievement', 'Commitment', 'Integrity', 'Transparency', 'Vision', 'Leadership Development', 'Team Work']

# Filter the data
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum().sum()
leadership_score = 100 - ((points_scored / total_points) * 100)
remaining_percentage = 100 - leadership_score

# donut chart
fig = go.Figure(go.Pie(
    labels=['Leadership Score', 'Remaining'],
    values=[leadership_score, remaining_percentage],
    hole=0.6,
    marker=dict(colors=['#FFB6C1', '#F8F8FF']),
    hoverinfo='label+percent',
    textinfo='label',
    showlegend=False
))

fig.update_layout(
    title='Leadership Score',
    annotations=[dict(text=f"{leadership_score:.2f}%", x=0.5, y=0.5, font_size=30, showarrow=False)],
)

fig.show()
In [10]:
# Plot for Team Collaboration Assessment
qualities = ['Teamwork', 'Trust', 'Conflict Resolution', 'Inclusiveness', 'Coaching/Mentoring', 'Communication', 'Reliability']

# Filter the data
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum().sum()
team_collaboration_score = 100 - ((points_scored / total_points) * 100)
remaining_percentage = 100 - team_collaboration_score

# donut chart
fig = go.Figure(go.Pie(
    labels=['Team Collaboration Score', 'Remaining'],
    values=[team_collaboration_score, remaining_percentage],
    hole=0.6,
    marker=dict(colors=['#FFB6C1', '#F8F8FF']),
    hoverinfo='label+percent',
    textinfo='label',
    showlegend=False
))

# layout properties
fig.update_layout(
    title='Team Collaboration Score',
    annotations=[dict(text=f"{team_collaboration_score:.2f}%", x=0.5, y=0.5, font_size=30, showarrow=False)],
)

fig.show()
In [11]:
# Plot for Employee Engagement
qualities = ['Empowerment', 'Recognition', 'Information Sharing', 'Well-Being', 'Sustainability', 'Community Involvement', 'Employee Engagement']

# Filter the data
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data[filtered_data['Selected_Value'] == 'Employee Engagement']['Value_Order'].sum()
employee_engagement_score = 100 -((points_scored / total_points) * 100)
remaining_percentage = 100 - employee_engagement_score

# donut chart
fig = go.Figure(go.Pie(
    labels=['Employee Engagement Score', 'Remaining'],
    values=[employee_engagement_score, remaining_percentage],
    hole=0.6,
    marker=dict(colors=['#FFB6C1', '#F8F8FF']),
    hoverinfo='label+percent',
    textinfo='label',
    showlegend=False
))

#  layout properties
fig.update_layout(
    title='Employee Engagement Score',
    annotations=[dict(text=f"{employee_engagement_score:.2f}%", x=0.5, y=0.5, font_size=30, showarrow=False)],
)

fig.show()
In [12]:
#Plot for the Innovation Mindset Assessment
qualities = ['Creativity', 'Continuous Improvement', 'Long-Term Perspective', 'Open Communication', 'Risk-Taking',
             'Change Averse', 'Decisiveness']

# Filter the data
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum().sum()
innovation_mindset_score = (points_scored / total_points) * 100
remaining_percentage = 100 - innovation_mindset_score

# donut chart
fig = go.Figure(go.Pie(
    labels=['Innovation Mindset Score', 'Remaining'],
    values=[innovation_mindset_score, remaining_percentage],
    hole=0.6,
    marker=dict(colors=['#FFB6C1', '#F8F8FF']),
    hoverinfo='label+percent',
    textinfo='label',
    showlegend=False
))

# layout properties
fig.update_layout(
    title='Innovation Mindset Score',
    annotations=[dict(text=f"{innovation_mindset_score:.2f}%", x=0.5, y=0.5, font_size=30, showarrow=False)],
)
fig.show()

Dashboard 1 : ends

Dashboard_2 : Current Cultural Values¶

  • Oraganisational Culture Assement : Tellss the current organisation score with the basis of employee reply
  • Change Management: Tells organisation change adaptibility
  • Organisational assessment : Tells the score how idea he defines organisation

q2.jpeg

In [13]:
# Overall understanding
assessments = {
    'Leadership Assessment': ['Accountability', 'Achievement', 'Commitment', 'Integrity', 'Transparency', 'Vision', 'Leadership Development', 'Team Work'],
    'Organizational Culture Assessment': ['Ethics', 'Excellence', 'Continuous Learning', 'Customer Satisfaction', 'Organizational Growth', 'Employee Engagement'],
    'Change Management Assessment': ['Open Communication', 'Adaptability', 'Innovation', 'Risk-Taking', 'Influence', 'Ease with Uncertainty', 'Patience', 'Personal Growth'],
    'Team Collaboration Assessment': ['Teamwork', 'Trust', 'Conflict Resolution', 'Inclusiveness', 'Coaching/Mentoring', 'Communication', 'Reliability'],
    'Employee Engagement Assessment': ['Empowerment', 'Recognition', 'Information Sharing', 'Well-Being', 'Sustainability', 'Community Involvement', 'Employee Engagement'],
    'Innovation Mindset Assessment': ['Creativity', 'Continuous Improvement', 'Long-Term Perspective', 'Open Communication', 'Risk-Taking', 'Change Averse', 'Decisiveness']
}

# overall score for each assessment
def calculate_overall_score(employee_id, qualities):
    filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
    total_points = len(filtered_data) * 10
    points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum()
    percentage_scores = (points_scored / total_points) * 100
    overall_score = percentage_scores.sum()
    return overall_score

# list to store overall scores
overall_scores = []

# assessments for the given Employee ID
for assessment, qualities in assessments.items():
    overall_score = calculate_overall_score(employee_id, qualities)
    overall_scores.append(overall_score)

# radial chart
fig = go.Figure()

# radial chart traces
fig.add_trace(go.Scatterpolar(
    r=overall_scores,
    theta=list(assessments.keys()),
    fill='toself',
    name='Score',
    marker=dict(color='purple')
))

# layout properties
fig.update_layout(
    polar=dict(
        radialaxis=dict(
            visible=True,
            range=[0, 100]
        )
    ),
    showlegend=False
)

fig.show()
In [14]:
#Plot for Change Management Assessment
qualities = ['Open Communication', 'Adaptability', 'Innovation', 'Risk-Taking', 'Influence', 'Ease with Uncertainty', 'Patience', 'Personal Growth']
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum().sum()
change_management_score = 100 - ((points_scored / total_points) * 100)
remaining_percentage = 100 - change_management_score

# donut chart
fig = go.Figure(go.Pie(
    labels=['Change Management Score', 'Remaining'],
    values=[change_management_score, remaining_percentage],
    hole=0.6,
    marker=dict(colors=['#FFB6C1', '#F8F8FF']),
    hoverinfo='label+percent',
    textinfo='label',
    showlegend=False
))

# layout properties
fig.update_layout(
    title='Change Management Score',
    annotations=[dict(text=f"{change_management_score:.2f}%", x=0.5, y=0.5, font_size=30, showarrow=False)],
)

fig.show()
In [15]:
# Plot for Organizational Culture Assessment
qualities = ['Ethics', 'Excellence', 'Continuous Learning', 'Customer Satisfaction', 'Organizational Growth', 'Employee Engagement']
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum().sum()
organizational_culture_score = 100 - ((points_scored / total_points) * 100)
remaining_percentage = 100 - organizational_culture_score

# donut chart
fig = go.Figure(go.Pie(
    labels=['Organizational Culture Score', 'Remaining'],
    values=[organizational_culture_score, remaining_percentage],
    hole=0.6,
    marker=dict(colors=['#FFB6C1', '#F8F8FF']),
    hoverinfo='label+percent',
    textinfo='label',
    showlegend=False
))

# layout properties
fig.update_layout(
    title='Organizational Culture Score',
    annotations=[dict(text=f"{organizational_culture_score:.2f}%", x=0.5, y=0.5, font_size=30, showarrow=False)],
)

fig.show()
In [16]:
# qualities to assess for the Change Management Assessment
qualities = ['Open Communication', 'Adaptability', 'Innovation', 'Risk-Taking', 'Influence', 'Ease with Uncertainty', 'Patience', 'Personal Growth']
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum()
percentage_scores = 100 - ((points_scored / total_points) * 100)

# plotly bar chart
fig = go.Figure(go.Bar(
    x=percentage_scores.values,
    y=percentage_scores.index,
    orientation='h',
    marker=dict(color='#FFB6C1'),
))

# layout properties
fig.update_layout(
    title='Change Management Trait Scores',
    xaxis=dict(title='Percentage'),
    yaxis=dict(title='Qualities'),
)

fig.show()
In [17]:
# qualities to assess for the Organizational Culture Assessment
qualities = ['Ethics', 'Excellence', 'Continuous Learning', 'Customer Satisfaction', 'Organizational Growth', 'Employee Engagement']
filtered_data = df[(df['Employee_ID'] == employee_id) & (df['Selected_Value'].isin(qualities))]
total_points = len(filtered_data) * 10
points_scored = filtered_data.groupby('Selected_Value')['Value_Order'].sum()
percentage_scores = (points_scored / total_points) * 100

# plotly bar chart
fig = go.Figure(go.Bar(
    x=percentage_scores.values,
    y=percentage_scores.index,
    orientation='h',
    marker=dict(color='#FFB6C1'),
))

# layout properties
fig.update_layout(
    title='Organizational Culture Trait Scores',
    xaxis=dict(title='Percentage'),
    yaxis=dict(title='Qualities'),
)

fig.show()

Dashboard2: ends

Dashboard 3: Desired Cultural values¶

  • Desired Changes Selected : Tells the suggestion given by employee for changes.

q3.jpeg

In [18]:
#creating new column with Value_Order with proper point
value_mapping = {1: 10, 2: 9, 3: 8, 4: 7, 5: 6, 6:5 , 7:4, 8:3 , 9:2, 10:1}
df['New_Value'] = df['Value_Order'].map(value_mapping)
print(df)

       Employee_ID  Question_ID          Selected_Value  Value_Order  \
0             2385          101          Accountability            1   
1             2385          101             Achievement            2   
2             2385          101              Commitment            3   
3             2385          101          Cost Reduction            4   
4             2385          101              Efficiency            5   
...            ...          ...                     ...          ...   
72145         1092          103          Cost Reduction            6   
72146         1092          103     Financial Stability            7   
72147         1092          103         Global Thinking            8   
72148         1092          103               Influence            9   
72149         1092          103  Leadership Development           10   

       New_Value  
0             10  
1              9  
2              8  
3              7  
4              6  
...          ...  
72145          5  
72146          4  
72147          3  
72148          2  
72149          1  

[72150 rows x 5 columns]
In [19]:
# Desired Changes
assessment_qualities = ['Compassion', 'Financial Stability', 'Customer Satisfaction', 'Global Thinking',
                       'Hierarchy', 'Job Security', 'Transparency', 'Information Sharing', 'Fairness', 'Cost Reduction']

filtered_data = df[df['Question_ID'] == 103]
filtered_data = filtered_data[filtered_data['Selected_Value'].isin(assessment_qualities)]

# Group the data by Selected_Value and calculate the sum of Value and count of Employee_ID
grouped_data = filtered_data.groupby('Selected_Value').agg({'New_Value': 'sum', 'Employee_ID': 'count'}).reset_index()

# bubble chart
fig = px.scatter(grouped_data, x='Selected_Value', y='New_Value', size='Employee_ID', hover_name='Selected_Value',
                 title='Bubble Chart for Assessment Question ID 103')

# layout properties
fig.update_layout(xaxis_title='Selected Value', yaxis_title='Value', showlegend=False)

fig.show()

Dashboard3: ends

Dashboard 4: Results of Survey¶

  • TreeMap
  • Selected Values
In [20]:
#Treemap
grouped_data = df.groupby('Selected_Value')['New_Value'].sum().reset_index()
fig = px.treemap(grouped_data, path=['Selected_Value'], values='New_Value')
fig.update_layout(title='Treemap Visualization')
fig.show()
In [21]:
#Barchart
bar_data = df[['Question_ID', 'Selected_Value', 'Value_Order']]
grouped_data = bar_data.groupby(['Question_ID', 'Selected_Value'])['Value_Order'].sum().reset_index()
sorted_data = grouped_data.groupby('Question_ID').apply(lambda x: x.sort_values('Value_Order', ascending=False)).reset_index(drop=True)

fig = go.Figure()

for question_id in sorted_data['Question_ID'].unique():
    question_data = sorted_data[sorted_data['Question_ID'] == question_id]
    fig.add_trace(go.Bar(x=question_data['Selected_Value'], y=question_data['Value_Order'], name=f'Question ID: {question_id}'))

# layout properties
fig.update_layout(
    barmode='group',
    title='Sum of Value_Order by Selected_Value (Separated by Question_ID)',
    xaxis_title='Selected_Value',
    yaxis_title='Sum of Value_Order'
)

fig.show()
In [ ]:
In [ ]: